Novel image feature alphabets for object recognition | IEEE Conference Publication | IEEE Xplore

Novel image feature alphabets for object recognition


Abstract:

Most successful object recognition systems are based on a visual alphabet of quantised gradient orientations. Here, we introduce two richer image feature alphabets for us...Show More

Abstract:

Most successful object recognition systems are based on a visual alphabet of quantised gradient orientations. Here, we introduce two richer image feature alphabets for use in object recognition. The two alphabets are evaluated using the PASCAL VOC challenge 2007 dataset. The results show that both alphabets perform as well as or better than the 'standard' gradient orientation based one.
Date of Conference: 08-11 December 2008
Date Added to IEEE Xplore: 23 January 2009
ISBN Information:
Print ISSN: 1051-4651
Conference Location: Tampa, FL, USA

References

References is not available for this document.